Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Legal testimony

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :)↵↵
    -0.06
    ā
    -0.06
    iy
    -0.06
     Families
    -0.06
    وز
    -0.06
     дан
    -0.06
    (Html
    -0.06
     farklı
    -0.06
    іка
    -0.06
    lararası
    -0.06
    POSITIVE LOGITS
    Wolf
    0.07
    _ray
    0.07
     illumination
    0.06
     doctr
    0.06
     komb
    0.06
     TLabel
    0.06
     deut
    0.06
    过程
    0.06
    (_:
    0.06
    ----------------
    0.06
    Act Density 0.007%

    No Known Activations